Papers › DSL-FIQA: Assessing Facial Image Quality via Dual-Set Degradation Learning and...

DSL-FIQA: Assessing Facial Image Quality via Dual-Set Degradation Learning and Landmark-Guided Transformer

13 Jun 2024CVPR 2024 1arXiv:2406.09622archive 2025-07-28

Wei-Ting Chen, Gurunandan Krishnan, Qiang Gao, Sy-Yen Kuo, Sizhuo Ma, Jian Wang

Generic Face Image Quality Assessment (GFIQA) evaluates the perceptual quality of facial images, which is crucial in improving image restoration algorithms and selecting high-quality face images for downstream tasks. We present a novel transformer-based method for GFIQA, which is aided by two unique mechanisms. First, a Dual-Set Degradation Representation Learning (DSL) mechanism uses facial images with both synthetic and real degradations to decouple degradation from content, ensuring generalizability to real-world scenarios. This self-supervised method learns degradation features on a global scale, providing a robust alternative to conventional methods that use local patch information in degradation learning. Second, our transformer leverages facial landmarks to emphasize visually salient parts of a face image in evaluating its perceptual quality. We also introduce a balanced and diverse Comprehensive Generic Face IQA (CGFIQA-40k) dataset of 40K images carefully designed to overcome the biases, in particular the imbalances in skin tone and gender representation, in existing datasets. Extensive analysis and evaluation demonstrate the robustness of our method, marking a significant improvement over prior methods.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

DSL-FIQA/DSL-FIQA mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Face Image QualityFace Image Quality AssessmentImage Quality AssessmentImage RestorationRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Face Image Quality Assessment CGFIQA-40k DSL-FIQA PLCC 0.9745 #1 of 3 Archive leaderboard report
Face Image Quality Assessment CGFIQA-40k DSL-FIQA SRCC 0.9740 #1 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections